Explainable Condition Monitoring via Probabilistic Anomaly Detection Applied to Helicopter Transmissions

TL;DR

This paper introduces an explainable, probabilistic anomaly detection method for condition monitoring that learns solely from healthy data, enabling fault detection and interpretability in safety-critical systems like helicopter transmissions.

Contribution

It proposes a novel Bayesian-based approach focusing on healthy data to detect anomalies, providing uncertainty quantification and interpretability for condition monitoring.

Findings

Achieves competitive detection performance on benchmark and real-world datasets.

Provides uncertainty estimates to support decision-making.

Enhances interpretability of anomaly detection results.

Abstract

We present a novel Explainable methodology for Condition Monitoring, relying on healthy data only. Since faults are rare events, we propose to focus on learning the probability distribution of healthy observations only, and detect Anomalies at runtime. This objective is achieved via the definition of probabilistic measures of deviation from nominality, which allow to detect and anticipate faults. The Bayesian perspective underpinning our approach allows us to perform Uncertainty Quantification to inform decisions. At the same time, we provide descriptive tools to enhance the interpretability of the results, supporting the deployment of the proposed strategy also in safety-critical applications. The methodology is validated experimentally on two use cases: a publicly available benchmark for Predictive Maintenance, and a real-world Helicopter Transmission dataset collected over multiple years. In both applications, the method achieves competitive detection performance with respect to state-of-the-art anomaly detection methods.